The detection of caffeine in a variety of beverages using Curie-point pyrolysis mass spectrometry and genetic programming

Freeze dried coffee, filter coffee, tea and cola were analysed by Curie-poi nt pyrolysis mass spectrometry (PyMS). Cluster analysis showed, perhaps not surprisingly, that the discrimination between coffee, tea and cola was ver y easy. However, cluster analysis also indicated that there was a secondary difference between these beverages which could be attributed to whether th ey were caffeine-containing or decaffeinated. Artificial neural networks (A NNs) could be trained, with the pyrolysis mass spectra from some of the fre eze dried coffees, to classify correctly the caffeine status of the unseen spectra of freeze dried coffee, filter coffee, tea and cola in an independe nt test set. However, the information in terms of which masses in the mass spectrum are important was not available, which is why ANNs are often perce ived as a 'black box' approach to modelling spectra. By contrast, genetic p rograms (GPs) could also be used to classify correctly the caffeine status of the beverages, but which evolved function trees (or mathematical rules) enabling the deconvolution of the spectra and which highlighted that m/z 67 , 109 and 165 were the most significant massed for this classification. Mor eover, the chemical structure of these mass ions could be assigned to the r eproducible pyrolytic degradation products from caffeine.